llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGLM 4.7

Zhipu AI model product

GLM 4.7

GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better terminal and multilingual coding, and a noticeable jump in UI output quality for modern, clean webpages and slides. You can use it in popular coding agents, call it via the Z.ai API, and even run it locally with public weights on HuggingFace and ModelScope using vLLM or SGLang.

Updated Aug 10, 2026. Default version: GLM-4.7

Compare
LLMBoard score66.2GLM-4.7
Coverage100%7 benchmark families
Context window204.8KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
GLM-4.7
Released
Dec 22, 2025
Knowledge cutoff
Apr 1, 2025
Parameters
358B
Context window
204.8K
Max output
131.1K
Inputs
text
Outputs
text
Open weights
Yes
License
MIT

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

GLM-4.7 category scores

Benchmark results

Published benchmark records for the scored version GLM-4.7.

13 rows
Columns

Show columns

Tau-bench0.92680.0%CAug 7, 2026
BrowseComp-zh0.751366.7%CAug 7, 2026
LiveCodeBench v60.8105382.7%CAug 7, 2026
IMO-AnswerBench0.8121938.9%CAug 7, 2026
Terminal-Bench0.3162537.5%CAug 7, 2026
AIME 20251.02111482.3%CAug 7, 2026
SWE-bench Multilingual0.7233433.3%CAug 7, 2026
MMLU-Pro0.82612980.5%CAug 7, 2026
Humanity's Last Exam0.4309268.1%CAug 7, 2026
SWE-Bench Verified0.73910463.1%CAug 7, 2026
BrowseComp0.5405831.6%CAug 7, 2026
Terminal-Bench 2.00.4444910.4%CAug 7, 2026
GPQA0.94823379.7%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

77 rows
Columns

Show columns

textindustry medicine and healthcare361463.0813N/AAug 6, 2026
text style controlindustry medicine and healthcare411480.8813N/AAug 6, 2026
textkorean431406.1159N/AAug 6, 2026
textenglish451453.65,564N/AAug 6, 2026
webdevwebdev-html451445.73,689N/AAug 6, 2026
webdevwebdev-react491424.499N/AAug 6, 2026
webdevoverall511433.53,796N/AAug 6, 2026
webdevwebdev511433.53,796N/AAug 6, 2026
textchinese541483.9685N/AAug 6, 2026
textindustry life and physical and social science541455.32,080N/AAug 6, 2026
text style controlkorean541406.8159N/AAug 6, 2026
textmulti turn561448.01,920N/AAug 6, 2026
text factualityenglish571457.35,305N/AAug 6, 2026
texthard prompts english601452.13,087N/AAug 6, 2026
textindustry legal and government601444.8954N/AAug 6, 2026
text style controlenglish601462.25,564N/AAug 6, 2026
text style controlindustry life and physical and social science601470.62,080N/AAug 6, 2026
text factualitymulti turn611456.31,331N/AAug 6, 2026
text factualityexclude ties621446.18,034N/AAug 6, 2026
text style controlmulti turn641459.21,920N/AAug 6, 2026
textindustry business and management and financial operations651428.42,241N/AAug 6, 2026
text factualityindustry entertainment and sports and media651412.01,610N/AAug 6, 2026
text style controlchinese651486.1685N/AAug 6, 2026
text style controlhard prompts english661472.93,087N/AAug 6, 2026
textexclude ties671431.58,362N/AAug 6, 2026
textrussian671427.21,354N/AAug 6, 2026
text factualitycreative writing671414.71,242N/AAug 6, 2026
text style controllonger query671451.43,079N/AAug 6, 2026
texthard prompts681443.86,590N/AAug 6, 2026
textcoding691455.82,410N/AAug 6, 2026
textlonger query691433.63,079N/AAug 6, 2026
text factualityindustry business and management and financial operations691443.71,560N/AAug 6, 2026
text factualityoverall701443.511,661N/AAug 6, 2026
textoverall711435.512,077N/AAug 6, 2026
text factualityindustry writing and literature and language711421.71,875N/AAug 6, 2026
text style controlhard prompts711462.76,590N/AAug 6, 2026
textindustry writing and literature and language721411.42,755N/AAug 6, 2026
text factualitynon english721427.86,268N/AAug 6, 2026
text style controlindustry legal and government721454.1954N/AAug 6, 2026
text style controlexclude ties731441.48,362N/AAug 6, 2026
textindustry entertainment and sports and media741402.22,381N/AAug 6, 2026
text factualitylonger query741448.62,249N/AAug 6, 2026
text style controloverall741441.812,077N/AAug 6, 2026
textpolish751424.7422N/AAug 6, 2026
text factualityhard prompts751462.86,302N/AAug 6, 2026
text style controlindustry business and management and financial operations751441.72,241N/AAug 6, 2026
textindustry software and it services761452.94,100N/AAug 6, 2026
text factualityindustry life and physical and social science761459.61,409N/AAug 6, 2026
text style controlindustry software and it services771474.34,100N/AAug 6, 2026
textnon english781416.06,513N/AAug 6, 2026
text factualityhard prompts english781467.82,255N/AAug 6, 2026
text style controlinstruction following781427.73,208N/AAug 6, 2026
text style controlpolish781426.2422N/AAug 6, 2026
text style controlindustry entertainment and sports and media791405.92,381N/AAug 6, 2026
text style controlindustry writing and literature and language791416.62,755N/AAug 6, 2026
textinstruction following801413.33,208N/AAug 6, 2026
text factualityrussian811427.4881N/AAug 6, 2026
text style controlcoding811485.52,410N/AAug 6, 2026
textcreative writing821402.01,912N/AAug 6, 2026
textgerman821419.6219N/AAug 6, 2026
text style controlrussian821432.21,354N/AAug 6, 2026
text style controlcreative writing831405.11,912N/AAug 6, 2026
text factualitycoding841480.31,690N/AAug 6, 2026
text style controlspanish851423.2314N/AAug 6, 2026
text factualityindustry software and it services861470.03,375N/AAug 6, 2026
text factualityinstruction following861423.32,341N/AAug 6, 2026
text style controlnon english861420.16,513N/AAug 6, 2026
text style controlgerman911421.1219N/AAug 6, 2026
text style controlmath911427.1695N/AAug 6, 2026
text style controlfrench931443.7267N/AAug 6, 2026
textfrench951427.8267N/AAug 6, 2026
textspanish951416.5314N/AAug 6, 2026
textmath961422.4695N/AAug 6, 2026
text style controlexpert1041443.5716N/AAug 6, 2026
textexpert1121418.1716N/AAug 6, 2026
text style controlindustry mathematical1131419.7538N/AAug 6, 2026
textindustry mathematical1211410.3538N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.25 input, $1.1 output per 1M via CrofAI
Tracked offerings
13
13 rows
Columns

Show columns

Zhipu AI Coding Planglm-4.7globalN/AN/A204.8KAug 7, 2026
Alibaba Coding Plan (China)glm-4.7globalN/AN/A202.8KAug 7, 2026
Alibaba Coding Planglm-4.7globalN/AN/A202.8KAug 7, 2026
KUAE Cloud Coding PlanGLM-4.7globalN/AN/A204.8KAug 7, 2026
Z.AI Coding Planglm-4.7globalN/AN/A204.8KAug 7, 2026
CrofAIglm-4.7global$0.25$1.1202.8KAug 7, 2026
302.AIglm-4.7global$0.286$1.14204.8KAug 7, 2026
LLM Gatewayglm-4.7global$0.38$1.98204.8KAug 7, 2026
DInferenceglm-4.7global$0.45$1.65200KAug 7, 2026
OpenCode Zenglm-4.7global$0.60$2.2204.8KAug 7, 2026
Z.AIglm-4.7global$0.60$2.2204.8KAug 7, 2026
Cortecsglm-4.7global$0.78$2.79202.8KAug 7, 2026
MoarkGLM-4.7global$3.5$14204.8KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

GLM 4.7 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

GLM-4.7Dec 22, 202566.2358B204.8K131.1KYesMIT

What is GLM 4.7?

A concise description based on the published model registry.

GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better terminal and multilingual coding, and a noticeable jump in UI output quality for modern, clean webpages and slides. You can use it in popular coding agents, call it via the Z.ai API, and even run it locally with public weights on HuggingFace and ModelScope using vLLM or SGLang.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

GLM 4.7 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

GLM 4.7vsMiMo V2.5 ProGLM 4.7vsGemma 4 26B A4BGLM 4.7vsGrok 4 FastGLM 4.7vsQwen3 235B A22B ThinkingGLM 4.7vsGLM 5.1GLM 4.7vsClaude Sonnet 3.7

Models similar to GLM 4.7

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#40-1.5
ZA

GLM 5.1

Zhipu AI

64.7 LLMBoard

DetailsCompare
#48-4.2
ZA

GLM 4.5

Zhipu AI

62.0 LLMBoard

DetailsCompare
#65-11.0
ZA

GLM 4.5 Air

Zhipu AI

55.1 LLMBoard

DetailsCompare
#10+14.1
ZA

GLM 5.2

Zhipu AI

80.3 LLMBoard

DetailsCompare
#37+0.1
XA

Grok 4 Fast

xAI

66.2 LLMBoard

DetailsCompare
#39-0.5
AC

Qwen3 235B A22B Thinking

Alibaba Cloud / Qwen Team

65.7 LLMBoard

DetailsCompare

FAQ

Common questions about GLM 4.7.

When was GLM 4.7 released?

GLM 4.7's default version was released on Dec 22, 2025.

How much does GLM 4.7 cost?

No official standard PAYG price is currently available for GLM 4.7. The lowest tracked third-party offer starts at $0.25 input and $1.1 output via CrofAI.

Who created GLM 4.7?

GLM 4.7 is published under Zhipu AI in the model registry.

What is the context window for GLM 4.7?

The default version has a 204.8K token context window.

Is GLM 4.7 open weight?

Yes. The default version is marked as open weight under MIT.

How many API providers offer GLM 4.7?

13 published provider offerings are linked to the default version.

What models should I compare GLM 4.7 with?

Nearby ranked alternatives include MiMo V2.5 Pro, Gemma 4 26B A4B, Grok 4 Fast.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai